CN108507787A - Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion and method - Google Patents
Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion and method Download PDFInfo
- Publication number
- CN108507787A CN108507787A CN201810689692.3A CN201810689692A CN108507787A CN 108507787 A CN108507787 A CN 108507787A CN 201810689692 A CN201810689692 A CN 201810689692A CN 108507787 A CN108507787 A CN 108507787A
- Authority
- CN
- China
- Prior art keywords
- wind power
- speed increase
- vibration
- gear speed
- noise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000002405 diagnostic procedure Methods 0.000 title claims abstract description 20
- 239000012530 fluid Substances 0.000 claims abstract description 73
- 238000001514 detection method Methods 0.000 claims abstract description 41
- 238000012360 testing method Methods 0.000 claims abstract description 36
- 239000008186 active pharmaceutical agent Substances 0.000 claims abstract description 23
- 238000002474 experimental method Methods 0.000 claims abstract description 22
- 238000009958 sewing Methods 0.000 claims abstract description 20
- 230000001133 acceleration Effects 0.000 claims abstract description 19
- 238000013135 deep learning Methods 0.000 claims abstract description 9
- 230000000694 effects Effects 0.000 claims abstract description 4
- 230000007257 malfunction Effects 0.000 claims description 29
- 239000006061 abrasive grain Substances 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000003062 neural network model Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 238000012952 Resampling Methods 0.000 claims description 12
- 238000013461 design Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 11
- 230000008901 benefit Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 238000011068 loading method Methods 0.000 claims description 5
- 239000002245 particle Substances 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 3
- 229910052742 iron Inorganic materials 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 3
- 238000003921 particle size analysis Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 13
- 239000000284 extract Substances 0.000 abstract description 10
- 239000003921 oil Substances 0.000 description 32
- 230000008878 coupling Effects 0.000 description 15
- 238000010168 coupling process Methods 0.000 description 15
- 238000005859 coupling reaction Methods 0.000 description 15
- 230000005611 electricity Effects 0.000 description 11
- 230000008859 change Effects 0.000 description 8
- 230000001050 lubricating effect Effects 0.000 description 8
- 238000009434 installation Methods 0.000 description 7
- 239000010687 lubricating oil Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006378 damage Effects 0.000 description 5
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000000306 component Substances 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000007812 deficiency Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 238000003754 machining Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000010304 firing Methods 0.000 description 2
- 238000000227 grinding Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000013011 mating Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000011900 installation process Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000006247 magnetic powder Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000005622 photoelectricity Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/257—Belief theory, e.g. Dempster-Shafer
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion and methods, solve the problems, such as the single detection method that wind power planetary gear speedup box fault diagnosis is faced, random wind loads special operation condition, interference of changing oil, with the high advantageous effect of fault diagnosis accuracy, scheme is as follows：Test platform includes：The experiment sewing platform base of Wind power gear speed increase box to be measured is set, vibration acceleration sensor, noise signal sensor is arranged in Wind power gear speed increase box side to be measured, Wind power gear speed increase box side to be measured is connect with fluid information detection sensor, each sensor is individually connect with data acquisition module, appraisal procedure can be directed to random wind loads operating mode and extract vibration performance index, extract noise characteristic index, for changing oil, interference problem extracts fluid characteristic index, to establish the vibration noise fluid Fusion Features assessment models based on deep learning and DS evidence theories.
Description
Technical field
The present invention relates to gearbox detection technique fields, more specifically to a kind of wind-powered electricity generation tooth based on multi-feature fusion
Take turns gearbox fault diagnostic test platform and method.
Background technology
Extensive with wind power plant builds up, and wind power generating set has been enter into the Frequent Troubles phase.Most wind field is in
Outlying area, farther out, Blower Body is higher, cannot advantageously carry out equipment routing inspection, maintenance down cost for distance between wind turbine
High therefore existing most of wind field is all to execute primary plan repair every half a year to safeguard.Currently, the failure of wind turbine is pre-
The alert SCADA system that the main monitoring room of wind power plant is depended on diagnostic mode, according to collected mass data, Centralizing inspection
With whole wind turbines of control wind power plant；But can not Accurate Diagnosis wind-driven generator initial failure, it is reliable to be badly in need of more intelligence
Method for diagnosing faults.
The intellectual monitoring of wind-driven generator and the important leverage that health maintenance is Wind Power Development, planetary gearbox is wind
The core component of power generator, each gear is also easy to produce the typical cases such as spot corrosion, crackle, abrasion in long-term random wind loads operating mode lower component
Earlier damage, potential significant damage.According to statistics, gear distress, proportion 60%, and tooth most easily occur in wind power equipment
The time of roller box maintenance, economic cost are high.Therefore, carry out the research of wind power planetary gear gearbox Incipient Fault Diagnosis, it can be with
Fault diagnosis accuracy rate is improved, prevents trouble before it happens, and save time and the cost of overhaul, meets the safe and healthy hair of wind-powered electricity generation energy industry
The demand of exhibition, has a vast market demand and industrialization prospect.
Vibration detection and oil liquid monitoring are common method for diagnosing faults.But in terms of vibration detection, due to wind-power electricity generation
Machine is influenced by random wind loads, and the input speed of wind-driven generator planetary gearbox is fluctuation, therefore wind-powered electricity generation planet tooth
The non-stationary feature highly significant of gearbox vibration signal is taken turns, traditional vibration signal fault signature extracts means can not be fine
Ground is analyzed by non-stationary signal；In terms of oil liquid monitoring, due to that can draw when wind power planetary gear gearbox more oil change
The change dramatically (interference problem of changing oil) for playing abrasive grain quantity in fluid, so traditional abrasive grain quantative attribute index can not be accurate
Reflect the physical fault state of wind power planetary gear gearbox.
On the other hand, traditional wind-driven generator planetary gearbox fault diagnosis detection method is often relatively simple,
The data only obtained by single detection means can not accurately reflect the malfunction of planetary gearbox, and testing result is deposited
In uncertainty；And the fault characteristic information that single detection means is reflected is not comprehensive, is only capable of carrying out from single level
Failure is extracted and analysis, and the multi-level comprehensive assessment of multi-angle can not be carried out to the malfunction of planetary gearbox.Cause
This lacks a kind of wind power planetary gear case fault condition detection appraisal procedure of multi information Fusion Features, also lacks corresponding wind-powered electricity generation
Planetary gearbox fault diagnostic test platform supports to provide easily test data.
In conclusion the detection method faced for wind power planetary gear speedup box fault diagnosis is single, random wind loads
Special operation condition, change oil interference the problems such as, research and develop wind power planetary gear gearbox fault diagnostic test platform and comprehensively, it is accurate,
The multi information Fusion Features check and evaluation method of intelligence, is of great significance.
Invention content
For overcome the deficiencies in the prior art, the present invention provides Wind power gear speed increase box failures based on multi-feature fusion
Diagnostic test platform, the test platform carry out fault message parallel acquisition using three kinds of vibration, fluid, noise detection means, can
It realizes and analyzing processing is carried out to fault message, the type and extent of gear destruction are fully characterized in terms of these three, not only significantly
The accuracy of fault diagnosis is improved, and extraction and analysis more fully has been carried out to fault signature from different perspectives.
In addition, the present invention provides a kind of wind power planetary gear case malfunction based on vibration-noise-fluid Fusion Features
Check and evaluation method, the fault detect appraisal procedure of this multicharacteristic information fusion can be directed to the extraction of random wind loads operating mode and shake
Dynamic characteristic index, extracts noise characteristic index, and for changing oil, interference problem extracts fluid characteristic index, is based on deeply to establish
Vibration-noise-fluid Fusion Features assessment models of degree study and DS evidence theories are conducive to improve wind power planetary gear speedup
Comprehensive, the intelligent and accuracy of box fault diagnosis.
The concrete scheme of Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion is as follows：
Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion, including：
Sewing platform base is tested, Wind power gear speed increase box to be measured, Wind power gear speed increase box output shaft setting to be measured can be arranged in surface
Load, load are connect by fixed axis gear case with Wind power gear speed increase box to be measured, and Wind power gear speed increase box input shaft passes through deceleration
Case is connect with servo motor, and servo motor is set to experiment sewing platform base, servo motor and PLC controller by servo motor mounting base
Connection；
Wind power planetary gear gearbox to be measured and vibration signal detection module, fluid information detecting module and noise measuring mould
Block is respectively connected with；The vibration signal detection module, fluid information detecting module and noise detection module respectively with PLC controller
It is connected.
The test platform carries out event by using the technological means of vibration signal equiangular sampling to Non-stationary vibration signal
Hinder feature-extraction analysis, it is accurate to Wind power gear speed increase box vibration signal fault signature extraction and analysis can effectively to reduce the fluctuation of speed
The influence of true property.
Further, the fluid information detecting module includes temperature sensor, online dielectric constant sensor, glues online
Spend sensor, online abrasive grain monitoring sensor and CMOS Debris Image sensors.Wherein, each sensor passes sequentially through screw thread company
The oil pipe T-type three-way interface mounted on wind power planetary gear gearbox lubricating system is connect, and the lubricating oil temperature detected is believed
Breath, lubricating oil water content information, lubricating oil viscosity information, wear debris size information and wear debris type information are sent to number
According to acquisition module.
Further, described Wind power gear speed increase box one end to be measured by oil pipe successively with fine filter, oil pump, coarse filtration
Device, cooler are connected with the fluid information detecting module, and oil pipe is connected to the other end of Wind power gear speed increase box to be measured.
Further, the fluid information detection sensor is by being threadably mounted at Wind power gear speed increase box end side oil to be measured
The interface of pipe.
Further, vibration signal detection module, including pulse signal acquisition device, several vibration acceleration sensors,
Pulse signal acquisition device is the photoelectric encoder mounted on Wind power gear speed increase box input shaft to be measured, vibration acceleration sensor
It is separately mounted to the bearing block and babinet at Wind power gear speed increase box both ends, vibration acceleration sensor and pulse signal acquisition device
By the collected angularly resampling vibration signal of institute, it is sent to data acquisition module (such as data collecting card).
Further, the PLC controller is connect with servo-driver, the operation of servo-driver control servomotor；Institute
It states servo motor and carries built-in encoder, servo motor operating parameters are fed back to PLC controller by built-in encoder, to realize
Closed-loop control to servo motor rotational speed and torque.
Industrial personal computer is connect with PLC controller, and PLC controller is connect with oil pump, directly controls the startup and closing of oil pump,
PLC controller is connected with load.Industrial personal computer sends out control parameter to PLC controller, and the PLC controller provides after calculating
Control parameter is simultaneously sent to servo-driver, the servo-driver control servomotor operation；It is carried on the servo motor
Motor operating parameters are fed back to control unit by built-in encoder, to realize the closed-loop control to servo motor rotational speed and torque.
Industrial personal computer is integrated with servo motor speed governing software systems, load regulation software systems, fault diagnosis software system.Into
When row detection, all devices of industrial personal computer firing test platform can be passed through.
Specifically, the input shaft on the left of wind power planetary gear gearbox to be measured passes through second shaft coupling and preposition reduction box
Output shaft is connected；Input shaft on the left of the preposition reduction box is connected by first shaft coupling with the output shaft of servo motor；Institute
It states the output shaft on the right side of wind power planetary gear gearbox to be measured and passes through third shaft coupling and the input shaft phase on the left of fixed axis gear case
Even；Output shaft on the right side of the fixed axis gear case is connected by the 4th shaft coupling with load, fixed axis gear case mounting base and load
Mounting base is the entity structure with kidney-shaped pilot hole and conical dowel pin hole.
Further, the Wind power gear speed increase box to be measured is set to the testing stand by Wind power gear speed increase box mounting base
Pedestal, load are set to experiment sewing platform base by loading mounting base, and fixed axis gear case is set to experiment by fixed axis gear case mounting base
Sewing platform base, reduction box are set to experiment sewing platform base by deceleration block.
Further, the Wind power gear speed increase box mounting base, load mounting base, fixed axis gear case mounting base and reduction box
Seat is detachably connected by bolt and experiment sewing platform base respectively.Each mounting base is with kidney-shaped pilot hole and conical dowel pin hole
Entity structure, mounting base are equipped with groove for fixing corresponding mechanism.
In addition, test platform further includes and power module, power module and servo motor, are made an uproar at vibration acceleration sensor
Acoustic signal sensor, fluid information detection sensor and PLC controller are individually connected to power.
By the acquisition to wind field random wind loads data, modeling and analyzing is carried out to the wind load under different operating modes,
Obtain corresponding random wind-force loading spectrum.Because research object is wind power planetary gear gearbox, wind power planetary gear gearbox
Input terminal only avoids the unnecessary wasting of resources there are one rotational speed and torque signal for short form test process, thus only need by
The random wind-force loading spectrum obtained is calculated to be turned at the rotating speed of wind-powered electricity generation planetary gearbox input terminal in driving chain of wind driven generator
Square signal.But the rotational speed and torque signal of wind power planetary gear gearbox input terminal has the characteristics that the big torque of the slow-speed of revolution, it is this
Signal not easily passs through mechanical equipment and directly generates and adjust, and may be used and increases retarder in wind power planetary gear gearbox front end
Mode carry out reverse " raising speed drop square ", the big dtc signal of the slow-speed of revolution is converted into the small dtc signal of high rotating speed and is controlled, and
It is originally inputted control signal using this signal as test platform, i.e. this test platform driving motor needs random wind loads to be simulated
Signal.Random wind loads whistle control system is made of industrial personal computer, PLC controller, servo-driver, four part of servo motor.System
When system operation, according to experiment demand in industrial personal computer input signal parameter, industrial personal computer sends out control parameter, PLC controls to PLC controller
Device processed provides control parameter after calculating, and servo-driver control servomotor is made to run；Encoder is carried on servo motor,
Motor operating parameters are fed back into control unit, to realize the closed-loop control to servo motor rotational speed and torque.
Installation process is built in test platform, the main rigging error for influencing platform measuring precision is in test platform
Driving motor, wind power planetary gear gearbox, each input and output shaft of the load motor generated coaxiality error in assembly.When
When coaxiality error does not meet matching standard, serious noise, vibration and soft impulse can be brought in equipment running process, it is right
Each parts of rotating machinery bring irreversible damage, seriously affect the service life of complete machine.Can be examination from the point of view of experiment
The collecting work for testing data brings interference, or even influences the accuracy of data.In order to reduce concentricity when each rotary shaft cooperation
Error, in addition to optimization structure during design and processing experiment rack installation pedestal and design parameter, each mating surface of improvement
Machining accuracy, also add modularization tunable arrangement.In the pedestal installation module of all rotating mechanisms, level side is devised
Upwards can precisely centering location structure, the intensity of positioning and debugging efforts of the equipment in assembling process can be effectively improved,
Realize precise positioning installation.Bolt positioning hole in wind power planetary gear gearbox mounting base be processed into kidney-shaped pilot hole make its
It along fine tuning is oriented in the horizontal direction of transmission shaft, can then utilize the positioning pin connection of mounting base design will when installation
The rigging position of wind turbine gearbox is accurately positioned, and each positioning bolt finally tightened in mounting base completes wind power planetary gear speedup
Assembly of the case mounting base on experiment sewing platform base.
This wind power planetary gear gearbox test platform integrates various faults collection apparatus scheme, using vibration, fluid, makes an uproar
Three kinds of detection means of sound carry out fault message parallel acquisition, and are carried out at analysis to fault message in industry control fault diagnosis system
Reason fully characterizes the malfunction of planetary gearbox in terms of these three.
The input shaft of wind power planetary gear gearbox often rotates a sampling angle, and photoelectric encoder collects a rotating speed
Pulse, pulse signal are sent to industrial personal computer；Industrial personal computer receives rotational speed pulse signal, is sent out to acceleration vibration signal sensor
Go out acquisition instructions once to acquire the acceleration vibration signal of wind power planetary gear gearbox；Collected acceleration at this time
Vibration signal is the angularly resampling vibration signal of wind power planetary gear gearbox, and the collected angularly resampling of institute is shaken
Dynamic signal is transferred into data acquisition module (being connect with industrial personal computer).
For overcome the deficiencies in the prior art, the present invention also provides a kind of based on vibration-noise-fluid Fusion Features
Wind power planetary gear case fault condition detection appraisal procedure, includes the following steps：
1) it is directed to the vibration performance index extraction of random wind loads operating mode；
2) noise characteristic index extraction；
3) it is directed to the fluid characteristic index extraction for interference problem of changing oil；
4) foundation of vibration-noise-fluid Fusion Features assessment models based on deep learning and DS evidence theories；
5) diagnostic assessment of wind power planetary gear gearbox malfunction.
The step 1) is as follows：
1-1) by the vibration signal detection module of test platform, relatively stable angularly resampling vibration signal number is obtained
According to；
It 1-2) is based on complete set empirical mode decomposition method, will the decomposition of resampling vibration signal be angularly a series of
Intrinsic mode component；
Optimal IMF signals 1-3) are filtered out according to kurtosis criterion, achieve the purpose that filtering and noise reduction；
Fourier transformation 1-4) is carried out to optimal IMF signals, obtains failure order feature spectrogram, and for the first time as instruction
Practice and build the vibration performance index of deep neural network assessment models.
The step 2) is as follows：
2-1) by the noise signal detection module of test platform, the noise signal number of wind power planetary gear gearbox is obtained
According to；
Acoustics calculation and analysis methods 2-2) are based on, obtain the sound pressure level and octave spectrum figure of noise signal, and made
For noise characteristic index；
The step 3) is as follows：
3-1) by the fluid information detecting module of test platform, fluid information database is obtained；
The quantity that different types of abrasive grain 3-2) is calculated based on method for analyzing iron spectrum accounts for the percentage of total abrasive grain quantity；
The quantity that the abrasive grain of different-grain diameter 3-3) is calculated based on laser particle size analysis method accounts for the percentage of total abrasive grain quantity；
3-4) by by the smaller abrasive type distribution proportion feature of interference effect of changing oil and Abrasive Particle Size distribution proportion feature,
As fluid characteristic index.
The step 4) is as follows：
Training sample set Φ 4-1) is established, as shown in formula (1), wherein ΦxFor x-th of training sample, Vx,Nx,OxGeneration respectively
The various single features indexs of x-th of training sample of table：Vibration performance index, noise characteristic index, fluid characteristic index；
4-2) divided in the significant advantage of image recognition, machine learning, big data processing analysis etc. based on deep learning
The various single features indexs that training sample is not concentrated are as input quantity, training and the depth for building various single features indexs
Neural network assessment models；The output quantity of model is wind power planetary gear gearbox malfunction；
The identification framework in DS evidence theories 4-3) is introduced into deep neural network assessment models, and with reference to depth nerve
The output quantity of network evaluation model determines malfunction identification framework Θ={ F of wind power planetary gear gearbox1,F2,…,
Fn, wherein F1, F2..., FnRepresent the n kind malfunctions of wind power planetary gear gearbox；
4-4) the advantage based on DS evidence theories in terms of multi-source feature fusion designs the deep learning-of multiple features
DS evidence theory fusion decision rules, key are that the deep neural network assessment models in conjunction with various single features indexs are come
Belief assignment function is described, as shown in formula (2)：
mi(F1, F2..., Fn, Θ) and=(piqi1, piqi2..., piqin, 1-pi) (2)
In formula, miRepresent the assessment result belief assignment letter of the deep neural network model of i-th kind of single features index
Number, i=1,2 ..., k, and the sum that k is the characteristic indexs such as vibration, noise, fluid；piRepresent i-th kind of single features index
Deep neural network model assessment result accuracy rate；qijRepresent the deep neural network model of i-th kind of single features index
By the confidence level that Samples Estimates are jth kind malfunction, j=1,2 ..., n；
For the Arbitrary Fault state F in malfunction identification framework Θj, the deep learning-DS evidence theories of multiple features
Fusion decision rule can use formula (3) and formula (4) to indicate：
It, can be by the assessment knot of its training sample set for the deep neural network model of various single features indexs in formula
Fruit accuracy rate is as piValue；qijValue can then be counted according to the assessment result of deep neural network model and be determined.
Step 5) is as follows：
New vibration, noise, fluid test data are constantly acquired by test platform, then extract its vibration performance respectively
Index, noise characteristic index, fluid characteristic index, form new sample to be tested, and input front established based on depth
Practise and DS evidence theories vibration-noise-fluid Fusion Features assessment models, the model can output planetary gear speedup case this
The malfunction at quarter, to realize the comprehensive, accurate of wind power planetary gear gearbox malfunction, intelligent diagnostics assessment.
Compared with prior art, the beneficial effects of the invention are as follows：
1) more means detections, the comprehensive wind-driven generator for extracting fault signature under a kind of random wind loads operating mode of present invention offer
Epicyclic gearbox test platform, the test platform integrate various faults collection apparatus scheme, utilize vibration, fluid, three kinds of noise
Detection means carries out fault message parallel acquisition, and carries out analyzing processing to fault message in industry control fault diagnosis system, from
The type and extent of these three aspects fully characterization gear destruction.The method for diagnosing faults of this Multi-information acquisition not only carries significantly
The high accuracy of fault diagnosis, and extraction and analysis more fully has been carried out to fault signature from different perspectives.
2) present invention provide it is a kind of effectively reduce rotating mechanism input, coaxiality error between output shaft towards assembly
Test-bed design.Optimize structure and design parameter during design and machining experiment rack installation pedestal, improve respectively
The machining accuracy of mating surface also adds modularization tunable arrangement.In the pedestal installation module of all rotating mechanisms, devise
In horizontal direction can precisely centering location structure, positioning and debugging efforts of the equipment in assembling process can be effectively improved
Intensity realizes precise positioning installation.
3) present invention provides a kind of wind-driven generator planetary gearbox test platform vibration inspection based on random wind loads
Module is surveyed, which can acquire the angularly resampling vibration signal of wind power planetary gear gearbox, turn to effectively reduce
Influence of the speed fluctuation to wind power planetary gear gearbox vibration signal fault signature extraction and analysis accuracy；
4) present invention provides a kind of oil liquid detection module, including temperature sensor, online dielectric constant sensor, online viscous
Sensor, online abrasive grain monitoring sensor and CMOS Debris Image sensors are spent, is connected through a screw thread and is separately mounted to gearbox
On the oil pipe T-type three-way interface of lubricating system, to realize the lubricating status and state of wear of Wind power gear speed increase box lubricating system
The on-line monitoring of (including wear type and degree of wear), while this mounting means is beneficial to safeguard and replace fault sensor
To realize the upgrading of detection module.
5) reverse " raising speed drop square " is carried out by the way of increasing retarder in Wind power gear speed increase box front end, by the slow-speed of revolution
Big dtc signal is converted to the small dtc signal of high rotating speed and is controlled, and simulates the wind that random wind-force loading spectrum calculates well
The big dtc signal of the Wind power gear speed increase box input terminal slow-speed of revolution in power generator transmission chain, and using this signal as test platform
It is originally inputted control signal.Experiment process is simplified, the unnecessary wasting of resources is avoided.
6) present invention provides a kind of wind power planetary gear case malfunction inspection based on vibration-noise-fluid Fusion Features
Appraisal procedure is surveyed, the fault detect appraisal procedure of this multicharacteristic information fusion can be directed to the extraction vibration of random wind loads operating mode
Characteristic index extracts noise characteristic index, and for changing oil, interference problem extracts fluid characteristic index, and depth is based on to establish
Vibration-noise-fluid Fusion Features assessment models of study and DS evidence theories are conducive to improve wind power planetary gear gearbox
Comprehensive, the intelligent and accuracy of fault diagnosis.
Description of the drawings
The accompanying drawings which form a part of this application are used for providing further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation do not constitute the improper restriction to the application for explaining the application.
Fig. 1 is positive structure schematic of the present invention；
Fig. 2 is overlooking structure diagram of the present invention；
Fig. 3 is Wind power gear speed increase box lubricating system schematic diagram；
Fig. 4 is fluid information detecting module schematic diagram；
Fig. 5 is data collecting system schematic diagram；
Fig. 6 is servo control system schematic diagram；
Fig. 7 is Wind power gear speed increase box fault diagnostic test platform scheme design diagram.
Fig. 8 is a kind of wind power planetary gear case fault condition detection assessment stream based on vibration-noise-fluid Fusion Features
Cheng Tu；
Wherein, 1, load fixed frame；2, it loads；3, the 4th shaft coupling；4, fixed axis gear case；5, third shaft coupling；6, it waits for
Survey Wind power gear speed increase box；7, vibration acceleration sensor；8, second shaft coupling；9, preposition reduction box；10, first shaft coupling；
11, servo motor；12, servo motor fixed frame；13, sewing platform base is tested；14, servo motor mounting base；15, preposition reduction box peace
Fill seat；16, Wind power gear speed increase box mounting base to be measured；17, fixed axis gear case mounting base；18, mounting base is loaded；19, photoelectricity is compiled
Code device；20, photoelectric encoder mounting base；21, the 5th shaft coupling；22, PLC controller；23, fluid information sensor；24, noise
Signal transducer；25, data acquisition module；26, industrial personal computer；27, servo-driver；28, overflow valve；29, fine filter；30、
Oil pump；31, coarse filter；32, cooler；33, CMOS Debris Images sensor；34, online abrasive grain monitoring sensor；35, exist
Line viscosity sensor；36, online dielectric constant sensor；37, temperature sensor.
Specific implementation mode
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the application.Unless another
It indicates, all technical and scientific terms used herein has usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific implementation mode, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative
It is also intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or combination thereof.
As background technology is introduced, the deficiencies in the prior art, in order to solve technical problem as above, this Shen
It please propose Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion.
In a kind of typical embodiment of the application, as shown in Figure 1, Wind power gear speed increase box based on multi-feature fusion
Fault diagnostic test platform, including experiment sewing platform base 13, experiment sewing platform base 13 are equipped with Wind power gear speed increase box mounting base 16；Wind
Wind power gear speed increase box 6 to be measured, the input in 6 left side of Wind power gear speed increase box to be measured are equipped in electric gear speedup case mounting base 16
Axis is connected by second shaft coupling 8 with the output shaft of preposition reduction box 9；The input shaft in 9 left side of preposition reduction box passes through first
Axis device 10 is connected with the output shaft of servo motor 11；The output shaft on 6 right side of Wind power gear speed increase box to be measured passes through third shaft coupling 5
It is connected with the input shaft in 4 left side of fixed axis gear case；The output shaft on 4 right side of fixed axis gear case passes through the 4th shaft coupling 3 and load phase
Even；The input shaft on 4 right side of fixed axis gear case extends shaft end and is connected with photoelectric encoder 19 by the 5th shaft coupling 21.
Power module provides power supply for the whole device of Wind power gear speed increase box fault diagnostic test rack；The load 2
Select magnetic powder brake.
Servo motor mounting base 14, preposition reduction box mounting base 15, Wind power gear speed increase box mounting base 16, fixed axis gear case
Mounting base 17 and load mounting base 18 are the entity structure with kidney-shaped pilot hole and conical dowel pin hole.
Servo motor 11 is fixed on servo motor fixed frame 12, the servo motor fixed frame by bolted connection
12 are fixed on servo motor mounting base 14 by bolted connection.
Preposition reduction box 9 is fixed on preposition reduction box mounting base 15 by bolted connection.Wind power gear speed increase box 6
It is fixed on Wind power gear speed increase box mounting base 16 by bolted connection.Fixed axis gear case 4 is by bolted connection
It is fixed on fixed axis gear case mounting base 17.Photoelectric encoder 19 is fixed on photoelectric encoder mounting base by bolted connection
20.Load 2 is fixed on load fixed frame 1 by bolted connection, and the load fixed frame 1 is by bolted connection
It is fixed on load mounting base 18.
Servo motor mounting base 14, preposition reduction box mounting base 15, Wind power gear speed increase box mounting base 16, fixed axis gear case
Mounting base 17, photoelectric encoder mounting base 20 and load mounting base 18 are fixed on experiment sewing platform base by bolted connection
13。
One end of Wind power gear speed increase box 6 to be measured by oil pipe successively with overflow valve 28, fine filter 29, oil pump 30, thick
Filter 31, cooler 32 are connected with fluid information detecting module, and last oil pipe is connected to the another of Wind power gear speed increase box 6 to be measured
One end constitutes Wind power gear speed increase box lubricating system；Oil pump 30 is connected with magnificent IPC-610L industrial personal computers 26 are ground.
Noise signal detection module includes noise signal sensor 24, and noise signal sensor 24 is mounted on wind-powered electricity generation tooth to be measured
Speedup box body is taken turns, the collected noise signal of institute is sent to data acquisition module 25, and then be sent to and grind magnificent IPC-610L
Industrial personal computer 26.
Fluid information detecting module, including temperature sensor 37, online dielectric constant sensor 36, online viscosity sensor
35, online abrasive grain monitoring sensor 34 and CMOS Debris Images sensor 33 are passed sequentially through threaded connection and are mounted on wind-powered electricity generation
On the oil pipe T-type three-way interface of gear speedup case lubricating system, and by the lubricating oil temperature information detected, lubricating oil water content
Information, lubricating oil viscosity information, wear debris size information and wear debris type information are sent to Siemens S7-200PLC control
The data acquisition module 25 of device 22 processed, and be sent to and grind magnificent IPC-610L industrial personal computers 26.
The vibration signal detection module, including pulse signal acquisition device, several vibration acceleration sensors 7, pulse
Signal pickup assembly is the photoelectric encoder 19 on wind power planetary gear gearbox input shaft to be measured, and vibration acceleration passes
Sensor 7 is separately mounted on the bearing block and babinet at 6 both ends of wind power planetary gear gearbox to be measured.Vibration acceleration sensor and
The collected angularly resampling vibration signal of institute is sent to data acquisition module 25, Jin Erchuan by pulse signal acquisition device
It send to grinding magnificent IPC-610L industrial personal computers 26.
It grinds magnificent IPC-610L industrial personal computers and sends out control parameter, Siemens S7-200PLC to Siemens S7-200PLC controller
Controller provides control parameter after calculating and is sent to servo-driver 27,27 control servomotor of the servo-driver
11 operations；Built-in encoder is carried on servo motor 11, motor operating parameters are fed back into control unit, to realize to servo
The closed-loop control of 11 rotational speed and torque of motor.
When being detected to Wind power gear speed increase box 6 to be measured, closed first according to 6 size design of Wind power gear speed increase box to be measured
Suitable survey Wind power gear speed increase box mounting base 16, and adjust Wind power gear speed increase box mounting base 16 and servo motor mounting base to be measured
14, the position of preposition reduction box mounting base 15, fixed axis gear case mounting base 17 and load mounting base 18 on experiment sewing platform base 13,
It is fixed on experiment sewing platform base 13 along the adjustment of waist type pilot hole respectively, Wind power gear speed increase box 6 to be measured is then placed on survey wind-powered electricity generation
Gear speedup case mounting base 16, is fixed with bolt, by the input shaft of Wind power gear speed increase box 6 to be measured and output shaft respectively with
Two shaft couplings 8 and third shaft coupling 5 connect, finally by the lubricating oil import/export of Wind power gear speed increase box 6 to be measured and wind-powered electricity generation tooth
Corresponding oil pipe connection in gearbox lubricating system is taken turns, vibration acceleration sensor 7 is placed on Wind power gear speed increase box 6 to be measured
Corresponding position.Power module provides power supply for the whole device of Wind power gear speed increase box fault diagnostic test rack.
It grinds magnificent IPC-610L industrial personal computers 26 and is integrated with servo motor speed governing software systems, load regulation software systems, failure
Diagnosing software system.It, can be by grinding all devices of magnificent IPC-610L industrial personal computers firing test platform when being detected.
Meanwhile photoelectric encoder 19, noise signal sensor 24, temperature sensor 37, online dielectric constant sensor 36,
Online viscosity sensor 35, online abrasive grain monitoring sensor 34 and CMOS Debris Images sensor 33 and vibration acceleration sensor
7 send the data measured to data acquisition module 25 by data line, and are sent to and grind magnificent IPC-610L industrial personal computers 26, grind China
IPC-610L industrial personal computers 26 will carry out gathered data processing analysis, and the acceleration after testing staff analyzes according to processing vibrates letter
Number, fluid information and noise signal be detected Wind power gear speed increase box 6.The present invention is by the acceleration of Wind power gear speed increase box
Vibration signal, fluid information and noise signal integrate consideration, realize and are more accurately detected to Wind power gear speed increase box.
In addition, the present invention also provides a kind of wind power planetary gear case failures based on vibration-noise-fluid Fusion Features
State-detection appraisal procedure, includes the following steps：
1) it is directed to the vibration performance index extraction of random wind loads operating mode；
2) noise characteristic index extraction；
3) it is directed to the fluid characteristic index extraction for interference problem of changing oil；
4) foundation of vibration-noise-fluid Fusion Features assessment models based on deep learning and DS evidence theories；
5) diagnostic assessment of wind power planetary gear gearbox malfunction.
It is as follows：
1) it is directed to the vibration performance index extraction of random wind loads operating mode；
First, by the vibration signal detection module of test platform, relatively stable angularly resampling vibration signal is obtained
Data；Then, complete set empirical mode decomposition method (complete ensemble empirical mode are based on
Decomposition with adaptive noise, abbreviation CEEMDAN), will the decomposition of resampling vibration signal be angularly one
The intrinsic mode component (intrinsic mode function, abbreviation IMF) of series；Then, it is filtered out most according to kurtosis criterion
Excellent IMF signals, achieve the purpose that filtering and noise reduction；Finally, Fourier transformation is carried out to optimal IMF signals, it is special obtains failure order
Spectrogram is levied, and for the first time as the vibration performance index of training and structure deep neural network assessment models.
2) noise characteristic index extraction；
First, by the noise signal detection module of test platform, the noise signal of wind power planetary gear gearbox is obtained
Data；Then, acoustics calculation and analysis methods are based on, obtain the sound pressure level and octave spectrum figure of noise signal, and as
Noise characteristic index.
3) it is directed to the fluid characteristic index extraction for interference problem of changing oil；
The change dramatically of abrasive grain quantity in fluid can be caused (to change oil dry when wind power planetary gear gearbox more oil change
Disturb problem), cause traditional abrasive grain quantative attribute index that can not accurately reflect the physical fault shape of wind power planetary gear gearbox
State；But under same state of wear, the abrasive grain of different wear types and grain size can still be formed according to the ratio before changing oil to be entered
In fluid, so the abrasive type ratio and Abrasive Particle Size ratio characteristic index in extraction fluid are to solve interference problem of changing oil
Break-through point.
First, by the fluid information detecting module of test platform, fluid information database is obtained；Then, iron is based on to compose
Analysis method calculates different types of abrasive grain, and (normal wear abrasive grain seriously slides abrasive grain, cutting wear particles, fatigue wear abrasive grain, oxygen
Change abrasive grain) quantity account for the percentage of total abrasive grain quantity；The abrasive grain of different-grain diameter is calculated subsequently, based on laser particle size analysis method
The quantity of (0-10 μm of grain size, 10-30 μm of grain size, 30-50 μm of grain size, 50-100 μm of grain size, 100 μm of grain size or more) accounts for total abrasive grain
The percentage of quantity；Finally, ratio will be distributed by the smaller abrasive type distribution proportion feature of interference effect of changing oil and Abrasive Particle Size
Example feature, as fluid characteristic index.
4) foundation of vibration-noise-fluid Fusion Features assessment models based on deep learning and DS evidence theories；
To improve the utilization rate of above-mentioned vibration, noise, fluid characteristic index, vibration performance index is integrated in fault location point
The sensitive advantage and fluid characteristic index of sensitive advantage, noise characteristic index in terms of the positioning of noise source in terms of analysis is in event
Hinder the sensitive advantage in terms of quantitative analysis, more comprehensively, accurately, intelligently assesses the malfunction of planetary gearbox, need
The intellectual technologies such as integrated application machine learning, Multi-source Information Fusion establish effective vibration-noise-fluid Fusion Features assessment
Model.Concrete scheme is as follows：
(1) training sample set Φ is established, as shown in formula (1), wherein ΦxFor x-th of training sample, Vx,Nx,OxGeneration respectively
The various single features indexs of x-th of training sample of table：Vibration performance index, noise characteristic index, fluid characteristic index.
(2) divided in the significant advantage of image recognition, machine learning, big data processing analysis etc. based on deep learning
The various single features indexs (vibration performance index, noise characteristic index, fluid characteristic index) that training sample is not concentrated are made
For input quantity, training and the deep neural network assessment models for building various single features indexs；The output quantity of model is wind-powered electricity generation
Planetary gearbox malfunction (such as gear wear, gear crack, bearing wear).
(3) identification framework in DS evidence theories is introduced into deep neural network assessment models, and with reference to depth nerve
The output quantity of network evaluation model determines malfunction identification framework Θ={ F of wind power planetary gear gearbox1,F2,…,
Fn, wherein F1, F2..., FnRepresent the n kind malfunctions of wind power planetary gear gearbox.
(4) advantage based on DS evidence theories in terms of multi-source feature fusion designs the deep learning-DS of multiple features
Evidence theory fusion decision rule, key are the deep neural network assessment models in conjunction with various single features indexs to retouch
Belief assignment function is stated, as shown in formula (2)：
mi(F1, F2..., Fn, Θ) and=(piqi1, piqi2..., piqin, 1-pi) (2)
In formula, miRepresent the assessment result belief assignment function of the deep neural network model of i-th kind of single features index, i
=1,2 ..., k, and the sum that k is the characteristic indexs such as vibration, noise, fluid；piRepresent the depth of i-th kind of single features index
Spend the assessment result accuracy rate of neural network model；qijThe deep neural network model of i-th kind of single features index is represented by sample
Originally the confidence level of jth kind malfunction, j=1,2 ..., n are evaluated as.
For the Arbitrary Fault state F in malfunction identification framework Θj, the deep learning-DS evidence theories of multiple features
Fusion decision rule can use formula (3) and formula (4) to indicate：
It, can be by the assessment knot of its training sample set for the deep neural network model of various single features indexs in formula
Fruit accuracy rate is as piValue；qijValue can then be counted according to the assessment result of deep neural network model and be determined.
(5) by test sample collection, to the deep neural network assessment models of various single features indexs carry out test with
It corrects, and improves the deep learning-DS evidence theory fusion decision rules of multiple features；It is based on deep learning and DS to establish
Vibration-noise of evidence theory-fluid Fusion Features assessment models.
5) diagnostic assessment of wind power planetary gear gearbox malfunction
New vibration, noise, fluid test data are constantly acquired by test platform, then extract its vibration performance respectively
Index, noise characteristic index, fluid characteristic index, form new sample to be tested, and input front established based on depth
It practises and vibration-noise-fluid Fusion Features assessment models of DS evidence theories, the model can intelligent independent ground output planetary tooth
The malfunction of gearbox this moment is taken turns, to realize comprehensive, the accurate, intelligent diagnostics of wind power planetary gear gearbox malfunction
Assessment.
The foregoing is merely the preferred embodiments of the application, are not intended to limit this application, for the skill of this field
For art personnel, the application can have various modifications and variations.Within the spirit and principles of this application, any made by repair
Change, equivalent replacement, improvement etc., should be included within the protection domain of the application.
Claims (10)
1. Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion, which is characterized in that including：
Sewing platform base is tested, Wind power gear speed increase box to be measured can be arranged in surface, and Wind power gear speed increase box output shaft setting to be measured loads,
Load is connect by fixed axis gear case with Wind power gear speed increase box to be measured, and Wind power gear speed increase box input shaft to be measured passes through reduction box
It is connect with servo motor, servo motor is set to experiment sewing platform base by servo motor mounting base, and servo motor connects with PLC controller
It connects；
Wind power planetary gear gearbox to be measured and vibration signal detection module, fluid information detecting module and noise detection module point
Xiang Lian not；The vibration signal detection module, fluid information detecting module and noise detection module respectively with PLC controller phase
Even.
2. Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion according to claim 1, special
Sign is, the fluid information detecting module include temperature sensor, online dielectric constant sensor, online viscosity sensor,
Online abrasive grain monitoring sensor and CMOS Debris Image sensors.
3. Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion according to claim 1, special
Sign is, described Wind power gear speed increase box one end to be measured by oil pipe successively with fine filter, oil pump, coarse filter, cooler
It is connected with the fluid information detecting module, oil pipe is connected to the other end of Wind power gear speed increase box to be measured.
4. Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion according to claim 1, special
Sign is that the Wind power gear speed increase box to be measured is set to the experiment sewing platform base, load by Wind power gear speed increase box mounting base
It is set to experiment sewing platform base by loading mounting base, fixed axis gear case is set to experiment sewing platform base by fixed axis gear case mounting base, subtracts
Fast case is set to experiment sewing platform base by deceleration block.
5. Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion according to claim 1, special
Sign is that the vibration signal detection module, including pulse signal acquisition device, several vibration acceleration sensors, pulse are believed
Number harvester is the photoelectric encoder mounted on Wind power gear speed increase box input shaft to be measured, and vibration acceleration sensor is pacified respectively
Bearing block and babinet mounted in Wind power gear speed increase box both ends, vibration acceleration sensor and pulse signal acquisition device will be adopted
The angularly resampling vibration signal collected, is sent to data acquisition module.
6. Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion according to claim 1, special
Sign is that the PLC controller is connect with servo-driver, and servo-driver controls the servo motor operation；The servo
Motor carries built-in encoder, and servo motor operating parameters are fed back to PLC controller by built-in encoder, to realize to servo
The closed-loop control of motor speed torque.
7. a kind of wind power planetary gear case fault condition detection appraisal procedure based on vibration-noise-fluid Fusion Features, special
Sign is, includes the following steps：
1) it is directed to the vibration performance index extraction of random wind loads operating mode；
2) noise characteristic index extraction；
3) it is directed to the fluid characteristic index extraction for interference problem of changing oil；
4) foundation of vibration-noise-fluid Fusion Features assessment models based on deep learning and DS evidence theories；
5) diagnostic assessment of wind power planetary gear gearbox malfunction.
8. a kind of wind power planetary gear case failure shape based on vibration-noise-fluid Fusion Features according to claim 7
State check and evaluation method, which is characterized in that the step 1) is as follows：
1-1) by the vibration signal detection module of test platform, relatively stable angularly resampling vibration signal data is obtained；
It 1-2) is based on complete set empirical mode decomposition method, will the decomposition of resampling vibration signal be angularly a series of intrinsic
Mode component；
Optimal IMF signals 1-3) are filtered out according to kurtosis criterion, achieve the purpose that filtering and noise reduction；
Fourier transformation 1-4) is carried out to optimal IMF signals, obtains failure order feature spectrogram, and for the first time as training and
Build the vibration performance index of deep neural network assessment models.
9. a kind of wind power planetary gear case failure shape based on vibration-noise-fluid Fusion Features according to claim 7
State check and evaluation method, which is characterized in that the step 2) is as follows：
2-1) by the noise signal detection module of test platform, the noise signal data of wind power planetary gear gearbox are obtained；
Acoustics calculation and analysis methods 2-2) are based on, obtain the sound pressure level and octave spectrum figure of noise signal, and as making an uproar
Acoustic signature index；
The step 3) is as follows：
3-1) by the fluid information detecting module of test platform, fluid information database is obtained；
The quantity that different types of abrasive grain 3-2) is calculated based on method for analyzing iron spectrum accounts for the percentage of total abrasive grain quantity；
The quantity that the abrasive grain of different-grain diameter 3-3) is calculated based on laser particle size analysis method accounts for the percentage of total abrasive grain quantity；
3-4) by by the smaller abrasive type distribution proportion feature of interference effect of changing oil and Abrasive Particle Size distribution proportion feature, as
Fluid characteristic index.
10. a kind of wind power planetary gear case failure based on vibration-noise-fluid Fusion Features according to claim 7
State-detection appraisal procedure, which is characterized in that the step 4) is as follows：
Training sample set Φ 4-1) is established, as shown in formula (1), wherein ΦxFor x-th of training sample, Vx,Nx,OxRespectively represent xth
The various single features indexs of a training sample：Vibration performance index, noise characteristic index, fluid characteristic index；
4-2) respectively will in the significant advantage of image recognition, machine learning, big data processing analysis etc. based on deep learning
The various single features indexs that training sample is concentrated are as input quantity, training and the depth nerve for building various single features indexs
Network evaluation model；The output quantity of model is wind power planetary gear gearbox malfunction；
The identification framework in DS evidence theories 4-3) is introduced into deep neural network assessment models, and with reference to deep neural network
The output quantity of assessment models determines malfunction identification framework Θ={ F of wind power planetary gear gearbox1,F2,…,Fn,
Middle F1, F2..., FnRepresent the n kind malfunctions of wind power planetary gear gearbox；
4-4) the advantage based on DS evidence theories in terms of multi-source feature fusion designs the deep learning-DS cards of multiple features
According to theoretical fusion decision rule, key is the deep neural network assessment models in conjunction with various single features indexs to describe
Belief assignment function, as shown in formula (2)：
mi(F1, F2..., Fn, Θ) and=(piqi1, piqi2..., piqin, 1-pi) (2)
In formula, miRepresent the assessment result belief assignment function of the deep neural network model of i-th kind of single features index, i=
1,2 ..., k, and the sum that k is the characteristic indexs such as vibration, noise, fluid；piRepresent the depth of i-th kind of single features index
The assessment result accuracy rate of neural network model；qijThe deep neural network model of i-th kind of single features index is represented by sample
It is evaluated as the confidence level of jth kind malfunction, j=1,2 ..., n；
For the Arbitrary Fault state F in malfunction identification framework Θj, the deep learning-DS evidence theory fusions of multiple features determine
Plan rule can use formula (3) and formula (4) to indicate：
It, can be accurate by the assessment result of its training sample set for the deep neural network model of various single features indexs in formula
True rate is as piValue；qijValue can then be counted according to the assessment result of deep neural network model and be determined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689692.3A CN108507787B (en) | 2018-06-28 | 2018-06-28 | Wind power gear speed increasing box fault diagnosis test platform and method based on multi-feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689692.3A CN108507787B (en) | 2018-06-28 | 2018-06-28 | Wind power gear speed increasing box fault diagnosis test platform and method based on multi-feature fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108507787A true CN108507787A (en) | 2018-09-07 |
| CN108507787B CN108507787B (en) | 2024-03-15 |
Family
ID=63404076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810689692.3A Active CN108507787B (en) | 2018-06-28 | 2018-06-28 | Wind power gear speed increasing box fault diagnosis test platform and method based on multi-feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108507787B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109597315A (en) * | 2018-10-31 | 2019-04-09 | 华中科技大学 | A kind of mechanical equipment health degenerate state discrimination method, equipment and system |
| CN109917287A (en) * | 2019-03-20 | 2019-06-21 | 华南理工大学 | Decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis |
| CN110146287A (en) * | 2019-06-10 | 2019-08-20 | 东北大学 | Offshore wind generating speed increaser reliability test bench |
| CN110378042A (en) * | 2019-07-23 | 2019-10-25 | 山东大学 | Gearbox of wind turbine oil temperature method for detecting abnormality and system based on SCADA data |
| CN110646200A (en) * | 2019-09-04 | 2020-01-03 | 天津工业大学 | Method for diagnosing weak local fault of gear of fixed shaft gear box |
| CN110844111A (en) * | 2019-10-11 | 2020-02-28 | 中国直升机设计研究所 | Multi-characteristic index bevel gear health state assessment method |
| CN111260640A (en) * | 2020-01-13 | 2020-06-09 | 重庆大学 | Tree generator network gear pitting image measuring method and device based on cyclean |
| CN111795817A (en) * | 2020-07-27 | 2020-10-20 | 西安交通大学 | RV reduction gear capability test device based on many sensing fuse |
| CN112362368A (en) * | 2021-01-14 | 2021-02-12 | 西门子交通技术(北京)有限公司 | Fault diagnosis method, device and system for train traction motor and readable medium |
| CN112729817A (en) * | 2021-02-04 | 2021-04-30 | 西南交通大学 | Gearbox fault diagnosis method, system and test bed based on multi-source data fusion |
| CN113340592A (en) * | 2021-06-03 | 2021-09-03 | 河北工业大学 | Involute gear abrasion and dynamics comprehensive experiment table considering external vibration excitation |
| CN113532848A (en) * | 2021-06-24 | 2021-10-22 | 南京工业大学 | Fault diagnosis system for planetary gear box |
| CN114018577A (en) * | 2021-09-28 | 2022-02-08 | 北京华控智加科技有限公司 | Equipment noise source imaging method and device, electronic equipment and storage medium |
| CN114063601A (en) * | 2021-11-12 | 2022-02-18 | 江苏核电有限公司 | Equipment state diagnosis system and method based on artificial intelligence |
| CN114136611A (en) * | 2021-12-01 | 2022-03-04 | 哈尔滨理工大学 | Gear reducer fault detection system |
| CN114383877A (en) * | 2021-12-31 | 2022-04-22 | 江苏核电有限公司 | System for be used for nuclear power station mechanical equipment failure diagnosis |
| CN115182983A (en) * | 2022-06-17 | 2022-10-14 | 同济大学 | Gear surface online monitoring imaging device based on gear box and control method |
| CN115630334A (en) * | 2022-10-26 | 2023-01-20 | 山东科技大学 | CBAM-based multi-channel feature fusion cross-domain mechanical fault diagnosis method and application |
| CN116091445A (en) * | 2023-01-05 | 2023-05-09 | 中国长江电力股份有限公司 | Ship lift gear and gear surface damage identification method based on deep learning |
| CN116379043A (en) * | 2023-04-11 | 2023-07-04 | 浙江勤鹏科技股份有限公司 | Fault detection method and system for spin-on oil filter |
| CN116758078A (en) * | 2023-08-18 | 2023-09-15 | 中科航迈数控软件(深圳)有限公司 | Speed change gear box observation method, system, terminal equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101566523A (en) * | 2009-05-11 | 2009-10-28 | 中能电力科技开发有限公司 | Method for monitoring state of gear case of wind generating set |
| US20100026006A1 (en) * | 2008-07-30 | 2010-02-04 | Yong Heun LEE | Power transmission apparatus for wind power generation and wind power generator using the same |
| CN103234585A (en) * | 2013-04-16 | 2013-08-07 | 内蒙古航天亿久科技发展有限责任公司 | Online monitoring and fault diagnosis system of large wind turbine units |
| CN103364189A (en) * | 2013-07-15 | 2013-10-23 | 中国水利电力物资华南公司 | Online fault diagnosis system of wind turbine generator gear case |
| CN103604601A (en) * | 2013-10-21 | 2014-02-26 | 浙江大学 | Fault diagnosis experiment platform based on wind power gearbox working condition simulation |
| CN104697787A (en) * | 2015-03-20 | 2015-06-10 | 山东大学 | Gearbox test bed based on multi-information fusion and detection method thereof |
| CN104764489A (en) * | 2015-03-27 | 2015-07-08 | 西安交通大学 | Online monitoring method for lubricating oil of wind-power transmission |
| CN106383028A (en) * | 2016-09-05 | 2017-02-08 | 北京航空航天大学 | Gear case fault diagnosis method |
| CN208254802U (en) * | 2018-06-28 | 2018-12-18 | 山东大学 | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion |
-
2018
- 2018-06-28 CN CN201810689692.3A patent/CN108507787B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100026006A1 (en) * | 2008-07-30 | 2010-02-04 | Yong Heun LEE | Power transmission apparatus for wind power generation and wind power generator using the same |
| CN101566523A (en) * | 2009-05-11 | 2009-10-28 | 中能电力科技开发有限公司 | Method for monitoring state of gear case of wind generating set |
| CN103234585A (en) * | 2013-04-16 | 2013-08-07 | 内蒙古航天亿久科技发展有限责任公司 | Online monitoring and fault diagnosis system of large wind turbine units |
| CN103364189A (en) * | 2013-07-15 | 2013-10-23 | 中国水利电力物资华南公司 | Online fault diagnosis system of wind turbine generator gear case |
| CN103604601A (en) * | 2013-10-21 | 2014-02-26 | 浙江大学 | Fault diagnosis experiment platform based on wind power gearbox working condition simulation |
| CN104697787A (en) * | 2015-03-20 | 2015-06-10 | 山东大学 | Gearbox test bed based on multi-information fusion and detection method thereof |
| CN104764489A (en) * | 2015-03-27 | 2015-07-08 | 西安交通大学 | Online monitoring method for lubricating oil of wind-power transmission |
| CN106383028A (en) * | 2016-09-05 | 2017-02-08 | 北京航空航天大学 | Gear case fault diagnosis method |
| CN208254802U (en) * | 2018-06-28 | 2018-12-18 | 山东大学 | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion |
Non-Patent Citations (6)
| Title |
|---|
| 唐政等: "基于DS证据理论的水下目标识别融合推理方法研究", 现代导航 * |
| 林丽;高建华;经昊达;王海洋;张向军;张秀丽;: "风机齿轮箱故障诊断与预警方法的研究进展", 仪器仪表与分析监测 * |
| 桂勇;韩勤锴;李峥;褚福磊;: "变速行星齿轮系统故障诊断方法", 振动.测试与诊断 * |
| 王绍进等: "基于决策层的提升机减速器故障诊断方法研究", 煤矿机械 * |
| 陈园艺: "风电机组齿轮箱故障诊断预警分析", 中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑） * |
| 陈康;陈良;耿臣露;王建明;: "基于深度学习的重载车辆齿轮箱的云故障诊断研究", 自动化应用 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109597315A (en) * | 2018-10-31 | 2019-04-09 | 华中科技大学 | A kind of mechanical equipment health degenerate state discrimination method, equipment and system |
| CN109917287B (en) * | 2019-03-20 | 2021-06-08 | 华南理工大学 | Speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis |
| CN109917287A (en) * | 2019-03-20 | 2019-06-21 | 华南理工大学 | Decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis |
| CN110146287A (en) * | 2019-06-10 | 2019-08-20 | 东北大学 | Offshore wind generating speed increaser reliability test bench |
| CN110378042A (en) * | 2019-07-23 | 2019-10-25 | 山东大学 | Gearbox of wind turbine oil temperature method for detecting abnormality and system based on SCADA data |
| CN110646200A (en) * | 2019-09-04 | 2020-01-03 | 天津工业大学 | Method for diagnosing weak local fault of gear of fixed shaft gear box |
| CN110646200B (en) * | 2019-09-04 | 2021-10-22 | 天津工业大学 | Method for diagnosing weak local fault of gear of fixed shaft gear box |
| CN110844111A (en) * | 2019-10-11 | 2020-02-28 | 中国直升机设计研究所 | Multi-characteristic index bevel gear health state assessment method |
| CN111260640A (en) * | 2020-01-13 | 2020-06-09 | 重庆大学 | Tree generator network gear pitting image measuring method and device based on cyclean |
| CN111260640B (en) * | 2020-01-13 | 2023-03-31 | 重庆大学 | Tree generator network gear pitting image measuring method and device based on cyclean |
| CN111795817A (en) * | 2020-07-27 | 2020-10-20 | 西安交通大学 | RV reduction gear capability test device based on many sensing fuse |
| CN112362368A (en) * | 2021-01-14 | 2021-02-12 | 西门子交通技术(北京)有限公司 | Fault diagnosis method, device and system for train traction motor and readable medium |
| CN112729817A (en) * | 2021-02-04 | 2021-04-30 | 西南交通大学 | Gearbox fault diagnosis method, system and test bed based on multi-source data fusion |
| CN113340592A (en) * | 2021-06-03 | 2021-09-03 | 河北工业大学 | Involute gear abrasion and dynamics comprehensive experiment table considering external vibration excitation |
| CN113532848A (en) * | 2021-06-24 | 2021-10-22 | 南京工业大学 | Fault diagnosis system for planetary gear box |
| CN114018577A (en) * | 2021-09-28 | 2022-02-08 | 北京华控智加科技有限公司 | Equipment noise source imaging method and device, electronic equipment and storage medium |
| CN114018577B (en) * | 2021-09-28 | 2023-11-21 | 北京华控智加科技有限公司 | Equipment noise source imaging method and device, electronic equipment and storage medium |
| CN114063601A (en) * | 2021-11-12 | 2022-02-18 | 江苏核电有限公司 | Equipment state diagnosis system and method based on artificial intelligence |
| CN114136611A (en) * | 2021-12-01 | 2022-03-04 | 哈尔滨理工大学 | Gear reducer fault detection system |
| CN114383877A (en) * | 2021-12-31 | 2022-04-22 | 江苏核电有限公司 | System for be used for nuclear power station mechanical equipment failure diagnosis |
| CN115182983A (en) * | 2022-06-17 | 2022-10-14 | 同济大学 | Gear surface online monitoring imaging device based on gear box and control method |
| CN115630334A (en) * | 2022-10-26 | 2023-01-20 | 山东科技大学 | CBAM-based multi-channel feature fusion cross-domain mechanical fault diagnosis method and application |
| CN115630334B (en) * | 2022-10-26 | 2024-05-03 | 山东科技大学 | CBAM-based cross-domain mechanical fault diagnosis method based on multi-channel feature fusion and application |
| CN116091445A (en) * | 2023-01-05 | 2023-05-09 | 中国长江电力股份有限公司 | Ship lift gear and gear surface damage identification method based on deep learning |
| CN116091445B (en) * | 2023-01-05 | 2024-01-02 | 中国长江电力股份有限公司 | Ship lift gear and gear surface damage identification method based on deep learning |
| CN116379043A (en) * | 2023-04-11 | 2023-07-04 | 浙江勤鹏科技股份有限公司 | Fault detection method and system for spin-on oil filter |
| CN116379043B (en) * | 2023-04-11 | 2024-03-08 | 浙江勤鹏科技股份有限公司 | Fault detection method and system for spin-on oil filter |
| CN116758078A (en) * | 2023-08-18 | 2023-09-15 | 中科航迈数控软件(深圳)有限公司 | Speed change gear box observation method, system, terminal equipment and storage medium |
| CN116758078B (en) * | 2023-08-18 | 2023-11-17 | 中科航迈数控软件(深圳)有限公司 | Speed change gear box observation method, system, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108507787B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108507787A (en) | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion and method | |
| CN208254802U (en) | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion | |
| CN108331718A (en) | Wind turbines yaw system monitors mechanism and fault diagnosis system and method on-line | |
| CN110469462B (en) | Wind turbine generator system intelligent state monitoring system based on multiple templates | |
| CN110926809B (en) | Big data analysis-based wind turbine generator transmission chain fault early warning method | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN104614179B (en) | A kind of gearbox of wind turbine state monitoring method | |
| CN104977047A (en) | Wind turbine online condition monitoring and health assessment system and method thereof based on vibration and oil | |
| CN103940611B (en) | Rolling bearing self adaptation method for detecting abnormality under a kind of Wind turbines variable working condition | |
| CN205260225U (en) | Long -range central monitoring system of health condition is synthesized to fan | |
| CN112213131B (en) | Rotary machine overhauls and fault diagnosis analog system | |
| CN101858778A (en) | Vibration monitoring-based wind generator set automatic fault diagnosis method | |
| CN103901882A (en) | Online monitoring fault diagnosis system and method of train power system | |
| CN106514433A (en) | Reliability test method and state monitoring system for chain tool magazine | |
| CN109542045A (en) | Numerically-controlled machine tool predictive maintenance standard testing bed and operating method | |
| CN108590984A (en) | A kind of wind generator set blade Payload Monitoring And Control method and device | |
| CN110186549A (en) | Blade vibration recognition methods based on Tip timing sensor | |
| CN103267873A (en) | Fault detecting system and method for propeller type anemometry sensor | |
| CN202661269U (en) | Compound fault diagnosis test platform of diesel engine | |
| CN115614292A (en) | Vibration monitoring device and method for vertical water pump unit | |
| CN202453182U (en) | Fault diagnosis device of gearbox of wind generation set | |
| Amin et al. | Vibration-based condition monitoring in wind turbine gearbox using convolutional neural network | |
| He et al. | Real-time fault diagnosis of motor bearing via improved cyclostationary analysis implemented onto edge computing system | |
| CN109281805A (en) | A kind of measuring multiple parameters intelligent inspection system | |
| CN201687699U (en) | Portable pump station unit state detection and data processing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |